New AI tool by IIT Hyderabad to Diagnose Brain Tumour without Surgery

The system employs radiomics, which extracts thousands of quantitative features, such as texture, shape, and intensity, from MRI images.

Researchers at IIT Hyderabad have developed an AI platform, RadGLO, which analyses MRI scans to diagnose brain tumours without any invasive procedures, such as surgical biopsy.

The AI-powered diagnostic tool uses crucial genetic-level insights directly from an MRI scan, enabling personalized, non-invasive treatment planning.

The system employs radiomics, which extracts thousands of quantitative features, such as texture, shape, and intensity, from MRI images. These features help in determining tumour grade, predicting treatment response, and forecasting survival outcomes.

Reportedly, two platforms were developed by the Researchers as a part of the project, which include RaSPr (Radiomic Survival Predictor) and RadGLO (Glioma Radiomics Analysis Platform).

The RaSpr uses radiomics features to detect the aggressiveness of the tumour and sort patients into high-risk (poor survival) and low-risk (better survival) groups, which is expected to allow doctors to make informed decisions.

While the RadGLO is an interactive web tool linking MRI features to nearly 20,000 genes and is designed to assist doctors in differentiating between aggressive and less aggressive gliomas, as well as understanding the tumour’s genetic basis.

The doctors can upload patient MRIs to RadGLO to receive automated risk predictions and molecular insights.

Stay tuned for more such updates on Digital Health News